The benefits of Mobile/Multi-access Edge Computing (MEC) are often discussed for reducing the latency and offloading intense computation for data processing of emerging applications on the user equipment (UE), such as Aug-mented/Virtual Reality (AR/VR), connected car, content delivery, etc., onto edge cloud. On the other hand, the performance of UE is rapidly improving with abundant resources for enabling local data processing. In this paper, we rethink the benefits of MEC by first arguing these benefits are myths, that is, the advancement of UE may defeat the often-assumed benefits of MEC, i.e., offloading computation and reducing latency, and then demystify the myths by carefully summarizing the latency and computational requirements of the existing applications possibly benefiting from MEC by surveying several tens of publications while examining the recent UEs performance improvement. We also attempt to undercover new benefits of MEC. In the light of these observations, we conclude that MEC is not necessarily just required for low-latency and computationally intensive applications, but also brings benefits from the four additional perspectives: (1) Data Scalability, (2) Application Scalability, (3) Intent-driven Networking, (4) Partial offloading of the network functions.